Thoughts of Machine Learning Enthusiasts

Kailyn 2022-11-19 23:30:37

1. The most impressive thing is that the team used a lot of data visualization to evaluate the running status of AlphaGo. Personally, I always thought that the most hard-core teams directly looked at the numbers. It seems that they will have to learn it in the future... 2. Huang Shijie's small draft is too cute 2333 3. Li Shishi's trance in the fourth game made me burst into tears. A mortal man forced the "God" to collapse by relying on his flesh and mortal fetus, how heroic this is! It is indeed a hand that can only be made by one in 10,000 human beings. 4. Everyone's comments on AlphaGo are very interesting. The first game is "it is like a top human chess player", and in the last game, "its play is beyond human understanding", just like reinforcement learning at the beginning. The intelligence of making bricks was imitating humans at first. After 300 games, he has figured out game skills that humans have not come up with. This feeling is too shocking. Machine learning may really become a tool for humans to re-understand the world. 5. Unfortunately, I didn't see how the team solved the problems that Fan Hui and Li Shishi forced AlphaGo to expose. I'm very interested in this, but I don't have the ability to read the paper...

View more about AlphaGo reviews

Extended Reading

AlphaGo quotes

  • Andrew Jackson: If DeepMind has figured out how to write code that doesn't have bugs, that is a bigger news story then AlphaGo.